English
Related papers

Related papers: Gate-Shift-Fuse for Video Action Recognition

200 papers

Effective processing of video input is essential for the recognition of temporally varying events such as human actions. Motivated by the often distinctive temporal characteristics of actions in either horizontal or vertical direction, we…

Computer Vision and Pattern Recognition · Computer Science 2020-06-24 Alexandros Stergiou , Ronald Poppe

Point cloud sequences are commonly used to accurately detect 3D objects in applications such as autonomous driving. Current top-performing multi-frame detectors mostly follow a Detect-and-Fuse framework, which extracts features from each…

Computer Vision and Pattern Recognition · Computer Science 2023-03-16 Chenhang He , Ruihuang Li , Yabin Zhang , Shuai Li , Lei Zhang

Graph Convolutional Networks (GCNs) have proven to be highly effective for skeleton-based action recognition, primarily due to their ability to leverage graph topology for feature aggregation, a key factor in extracting meaningful…

Computer Vision and Pattern Recognition · Computer Science 2025-09-10 Haiqing Ren , Zhongkai Luo , Heng Fan , Xiaohui Yuan , Guanchen Wang , Libo Zhang

In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Our motivation stems from the observation that 2D CNNs applied to individual frames of the video have…

Computer Vision and Pattern Recognition · Computer Science 2018-04-13 Du Tran , Heng Wang , Lorenzo Torresani , Jamie Ray , Yann LeCun , Manohar Paluri

Recently skeleton-based action recognition has made signif-icant progresses in the computer vision community. Most state-of-the-art algorithms are based on Graph Convolutional Networks (GCN), andtarget at improving the network structure of…

Computer Vision and Pattern Recognition · Computer Science 2020-08-04 Zeshi Yang , Kangkang Yin

Graph convolutional networks (GCNs) are widely adopted in skeleton-based action recognition due to their powerful ability to model data topology. We argue that the performance of recent proposed skeleton-based action recognition methods is…

Computer Vision and Pattern Recognition · Computer Science 2022-04-01 Liyu Wu , Can Zhang , Yuexian Zou

Monocular scene flow estimation aims to recover dense 3D motion from image sequences, yet most existing methods are limited to two-frame inputs, restricting temporal modeling and robustness to occlusions. We propose RAFT-MSF++, a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Xunpei Sun , Zuoxun Hou , Yi Chang , Gang Chen , Wei-Shi Zheng

Non-uniformed 3D sparse data, e.g., point clouds or voxels in different spatial positions, make contribution to the task of 3D object detection in different ways. Existing basic components in sparse convolutional networks (Sparse CNNs)…

Computer Vision and Pattern Recognition · Computer Science 2022-04-27 Yukang Chen , Yanwei Li , Xiangyu Zhang , Jian Sun , Jiaya Jia

Also recently, exciting strides forward have been made in the area of image restoration, particularly for image denoising and single image super-resolution. Deep learning techniques contributed to this significantly. The top methods differ…

Computer Vision and Pattern Recognition · Computer Science 2016-07-27 Jiqing Wu , Radu Timofte , Luc Van Gool

Recent studies have witnessed the effectiveness of 3D convolutions on segmenting volumetric medical images. Compared with the 2D counterparts, 3D convolutions can capture the spatial context in three dimensions. Nevertheless, models…

Image and Video Processing · Electrical Eng. & Systems 2021-09-28 Junjun He , Jin Ye , Cheng Li , Diping Song , Wanli Chen , Shanshan Wang , Lixu Gu , Yu Qiao

Skeleton-based Graph Convolutional Networks (GCNs) models for action recognition have achieved excellent prediction accuracy in the field. However, limited by large model and computation complexity, GCNs for action recognition like 2s-AGCN…

Hardware Architecture · Computer Science 2021-08-03 Dong Wen , Jingfei Jiang , Jinwei Xu , Kang Wang , Tao Xiao , Yang Zhao , Yong Dou

Deriving an effective facial expression recognition component is important for a successful human-computer interaction system. Nonetheless, recognizing facial expression remains a challenging task. This paper describes a novel approach…

Computer Vision and Pattern Recognition · Computer Science 2019-04-15 Mundher Al-Shabi , Wooi Ping Cheah , Tee Connie

Multiscale convolutional neural network (CNN) has demonstrated remarkable capabilities in solving various vision problems. However, fusing features of different scales alwaysresults in large model sizes, impeding the application of…

Computer Vision and Pattern Recognition · Computer Science 2024-01-23 Rui Huang , Qingyi Zhao , Yan Xing , Sihua Gao , Weifeng Xu , Yuxiang Zhang , Wei Fan

Existing 3D skeleton-based action recognition approaches reach impressive performance by encoding handcrafted action features to image format and decoding by CNNs. However, such methods are limited in two ways: a) the handcrafted action…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Shannan Guan , Haiyan Lu , Linchao Zhu , Gengfa Fang

We tackle the task of scene flow estimation from point clouds. Given a source and a target point cloud, the objective is to estimate a translation from each point in the source point cloud to the target, resulting in a 3D motion vector…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Yushan Zhang , Johan Edstedt , Bastian Wandt , Per-Erik Forssén , Maria Magnusson , Michael Felsberg

Most action recognition solutions rely on dense sampling to precisely cover the informative temporal clip. Extensively searching temporal region is expensive for a real-world application. In this work, we focus on improving the inference…

Computer Vision and Pattern Recognition · Computer Science 2021-07-30 Chunhui Liu , Xinyu Li , Hao Chen , Davide Modolo , Joseph Tighe

Temporal modelling is the key for efficient video action recognition. While understanding temporal information can improve recognition accuracy for dynamic actions, removing temporal redundancy and reusing past features can significantly…

Computer Vision and Pattern Recognition · Computer Science 2021-02-12 Yue Meng , Rameswar Panda , Chung-Ching Lin , Prasanna Sattigeri , Leonid Karlinsky , Kate Saenko , Aude Oliva , Rogerio Feris

Neural networks for visual content understanding have recently evolved from convolutional ones (CNNs) to transformers. The prior (CNN) relies on small-windowed kernels to capture the regional clues, demonstrating solid local expressiveness.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Zixuan Su , Hao Zhang , Jingjing Chen , Lei Pang , Chong-Wah Ngo , Yu-Gang Jiang

In this paper, we present Fusion-GCN, an approach for multimodal action recognition using Graph Convolutional Networks (GCNs). Action recognition methods based around GCNs recently yielded state-of-the-art performance for skeleton-based…

Computer Vision and Pattern Recognition · Computer Science 2021-09-28 Michael Duhme , Raphael Memmesheimer , Dietrich Paulus

As a fundamental part of computational healthcare, Computer Tomography (CT) and Magnetic Resonance Imaging (MRI) provide volumetric data, making the development of algorithms for 3D image analysis a necessity. Despite being computationally…

Image and Video Processing · Electrical Eng. & Systems 2023-07-26 C. I. Ugwu , S. Casarin , O. Lanz